+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Open Weight (https://www.datasculpting.ai/inference/forumdisplay.php?fid=49)
+---- Forum: Recipes & Configurations (https://www.datasculpting.ai/inference/forumdisplay.php?fid=52)
+---- Thread: model fallback rules that work: anyone testing this? (/showthread.php?tid=227)
model fallback rules that work: anyone testing this? - kernelpeak - 09-11-2026
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once router policy becomes important.
Interested in tradeoffs more than fan loyalty.
Re: model fallback rules that work: anyone testing this? - labpath - 09-12-2026
Quote:Spent some time on this today and wanted to compare notes.
I'd start with the simpler stack.
Re: model fallback rules that work: anyone testing this? - pixelcrate82 - 09-12-2026
worth checking the driver first.